1.
|
Q-learning is the most popular and effective version of Reinforcement Learning algorithms. In this paper we discuss the possibility of control of a nonstationary system b [...]
|
2.
|
Velichová, D.
Intrinsic geometric properties of a solid are presented as derived from the solid analytic representation in the form of a point function in three real variables. The sol [...]
|
3.
|
GEORGOPOULOS, Costas
The challenge of learning conceptual design at universities is exacerbated with the introduction of sustainability that is a relatively new and fast evolving subject. The [...]
|
4.
|
Locally Weighted Learning (LWR) is a class of approximations, based on a local model. In this paper we demonstrate using LWR together with Q-learning for control tasks. Q [...]
|
5.
|
Q-learning method proved to be usable in active magnetic bearing (AMB) control task, however the learning speed remains the main problem. Two-phase variant of the Q-learn [...]
|
6.
|
Marada, Tomáš
Abstrakt: Tento článek obsahuje numerické experimenty, popisujicí nastaveni parametrů Q-učeni pro řízeni asynchronniho elektromotoru. Citem je stanovit velikost a [...]
|
7.
|
Asynchronous electric motor control task can be successfully solved using reinforcement learning based method called Q-learning. The main problem to solve is the converge [...]
|
8.
|
Modifications of reinforcement learning algorithm, so called continuous action reinforcement learning automaton (CARLA), are presented in this contribution. Automaton lea [...]
|